© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 257607
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    メール
    0.55
    נת
    0.49
    ัท
    0.45
    йом
    0.44
    イド
    0.44
     Robotics
    0.44
    ﭼ
    0.44
    यदि
    0.43
    。
    0.43
     Nautical
    0.43
    POSITIVE LOGITS
     faker
    0.50
     तालुका
    0.48
     pienso
    0.46
     मुद्दे
    0.45
    朊
    0.45
     сосредото
    0.44
     vir
    0.44
     एक्सप्ले
    0.44
    ğa
    0.43
    ofacial
    0.43
    Activations Density 0.000%

    No Known Activations